AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

A Generalized Earley Parser for Human Activity Parsing and Prediction

Siyuan Qi, Baoxiong Jia, Siyuan Huang, Ping Wei, Song Chun Zhu

TPAMI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 43 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add generalized Earley parser on classifier outputsBi-LSTM · CAD-120 detectionmicro accuracy (P/R, %): 76.2 -> 79.4Improved
add generalized Earley parser on classifier outputsBi-LSTM · CAD-120 future 3s predictionmicro accuracy (P/R, %): 54.2 -> 61.5Improved
add generalized Earley parser on classifier outputsBi-LSTM · CAD-120 segment predictionmicro accuracy (P/R, %): 31.4 -> 72.2Improved
add generalized Earley parser on classifier outputsBi-LSTM · Watch-n-Patch detectionmicro accuracy (P/R, %): 84.0 -> 84.8Improved
add generalized Earley parser on classifier outputsBi-LSTM · Watch-n-Patch future 3s predictionmicro accuracy (P/R, %): 42.1 -> 49.0Improved
add generalized Earley parser on classifier outputsBi-LSTM · Watch-n-Patch segment predictionmicro accuracy (P/R, %): 21.7 -> 35.6Improved
use generalized Earley parser instead of original Earley on segmented labelsST-AOG + Earley · CAD-120 segment predictionmicro accuracy (P/R, %): 54.3 -> 72.2Improved
use generalized Earley parser instead of original Earley on segmented labelsST-AOG + Earley · Watch-n-Patch segment predictionmicro accuracy (P/R, %): 29.4 -> 35.6Improved
use generalized Earley parser instead of original Earley on segmented labelsST-AOG + Earley · CAD-120 detectionmicro accuracy (P/R, %): 76.5 -> 79.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy